tools/ai/claude/config/skills/glossary/SKILL.md
Use when the user wants to nail down domain terms, resolve terminology ambiguities, or build a shared language for a module or repo. Drills vocabulary one question at a time and writes to the project GLOSSARY.md.
npx skillsauth add pixelastic/oroshi glossaryInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Drills domain vocabulary one question at a time, then writes to the project GLOSSARY.md.
Goal: Identify which GLOSSARY.md to write to.
Exit criterion: Target file path is known.
Infer from context:
<module>/GLOSSARY.mdGLOSSARY.mdIf the file already exists, read it before drilling — don't duplicate or contradict existing terms.
Goal: Resolve every term one at a time.
Exit criterion: All terms are settled and the user confirms the glossary is ready to write.
Interview me relentlessly about every term of this plan until we reach a shared understanding. Walk down each branch of the design tree, resolving dependencies between decisions one-by-one. For each question, provide your recommended answer.
Ask the questions one at a time, waiting for feedback on each question before continuing.
Wait for an answer before moving to the next question.
Once all terms are resolved, present a summary and ask: "Ready to write the glossary?"
Challenge against the glossary:
When I uses a term that conflicts with the existing language in GLOSSARY.md, call it out immediately.
Example: "Your glossary defines 'cancellation' as X, but you seem to mean Y — which is it?"
Sharpen fuzzy language: When I uses vague or overloaded terms, propose a precise canonical term. Example: "You're saying 'account' — do you mean the Customer or the User? Those are different things."
Discuss concrete scenarios: When domain relationships are being discussed, stress-test them with specific scenarios. Invent scenarios that probe edge cases and force the user to be precise about the boundaries between concepts.
Cross-reference with code: When I state how something works, check whether the code agrees. If you find a contradiction, surface it: "Your code cancels entire Orders, but you just said partial cancellation is possible — which is right"
Goal: Write the complete glossary to the target file.
Exit criterion: File written and confirmed.
Update the glossary — all terms, relationships, flagged ambiguities, and example dialogue.
Use the format in GLOSSARY-FORMAT.md.
Goal: Keep the root GLOSSARY.md as an accurate index of all sub-module glossaries.
Exit criterion: Root file lists this sub-module glossary with a current one-line description.
Skip if: Skip this step if the target file IS the root GLOSSARY.md.
Update the root GLOSSARY.md to reference the updated sub-glossary.
Use the format in GLOSSARY-INDEX-FORMAT.md.
| Rationalization | Reality | |---|---| | "I'll write each term as it's resolved" | Relationships need all terms. Write once, at the end. | | "Target is obvious from context" | One question beats writing to the wrong file. | | "I know this term from prior context" | Prior context isn't canonical. Drill it. |
tools
Turn the current conversation context into a PRD and publish it to the project issue tracker. Use when user wants to create a PRD from the current context.
tools
Break a plan, spec, or PRD into independently-grabbable issues using tracer-bullet vertical slices. Use when user wants to convert a plan into issues, create implementation tickets, or break down work into issues.
documentation
Use when user says "sidequest" or "handoff" — compact conversation context into a document for a fresh agent to pick up.
documentation
Use when writing or modifying ZSH functions.